Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    dates in varied contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of departure or leaving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pitted
    -0.68
    RGB
    -0.67
    Gallery
    -0.66
     Ratings
    -0.66
    Glass
    -0.66
     compares
    -0.63
    als
    -0.63
    vre
    -0.61
     aired
    -0.61
    Reviewer
    -0.60
    POSITIVE LOGITS
     reinforcements
    0.82
     disillusion
    0.76
     voluntarily
    0.75
     disgrace
    0.74
     fleeing
    0.73
     pledging
    0.73
     wiser
    0.71
    quit
    0.71
     remorse
    0.70
     notation
    0.70
    Act Density 0.532%

    No Known Activations